Autonomous AI agents that perform tasks independently
Gregory Provo
Per-API-call token cost decomposition for Claude Code, Claude desktop agents, and Cursor.
kojiltd
Soul Compiler by Koji Limited (Hong Kong AI venture studio) — compiles character DNA for AI agents, not prompts.
dennisbiber
A passive policy-enforcement layer for agent tool calls
galimba
A Claude-Code-first, external control-plane template for regulated small teams that need auditable, human-gated, containerized AI-assisted development without embedding governance machinery inside target repositories.
...morebartoszarendt
Practical loop engineering for AI coding agents: scoped task records, orchestrator/maintainer/engineer roles, fresh verification evidence, and review gates — so complex work runs for hours without drifting scope or grading its own exam. Markdown-first; works with OpenCode, Claude Code, Codex, Copilot, and Cursor.
...moreMagentic
Verdict policy language (VPL) lexer, parser, and compiler to VIR. Also compiles the JSON policy form.
Magentic
Verdict embedded evaluator: VIR interpreter, decision combining, tracing, caches. Zero network calls; runs on Workers, Lambda, Bun, Deno, Node.
...moreMagentic
Verdict storage abstraction and adapters: in-memory, SQL (SQLite/D1/Postgres via minimal drivers), and object storage (filesystem, R2/S3-compatible).
...moreMagentic
Verdict async audit pipeline: batching sink with bounded buffering, retry, drop accounting, and queue adapters. Decisions never block on audit I/O.
...moreMagentic
Verdict client SDK for JavaScript/TypeScript: one interface (check, batchCheck, authorize, explain, simulate) over embedded engines, hybrid SyncedVerdict, or a remote PDP.
...moreMagentic
Verdict control-plane services: policy lifecycle (draft/validate/simulate/publish/rollback), tenant bundle builder with Ed25519 signing, API key management.
...moreMagentic
Verdict hybrid-mode sync client: local evaluation over bundles synced from a control plane. ETag polling, SSE, WebSocket, and push transports; signature verification, replay protection, staleness policies, rollback ring.
...moreMagentic
Verdict remote PDP and management API (Hono). Runs on Workers, Lambda, Deno, Bun, Node, and containers.
Magentic
Verdict domain types, wire contracts, and runtime guards. Zero dependencies; runs on Workers, Lambda, Bun, Deno, Node.
AgentCulture
Maps the geometry of meaning produced by embedding models — survey a corpus into a semantic landscape, then inspect its regions, neighborhoods, directions, and gaps, and compare models. Backs a Surveyor agent that runs measured experiments against the space and records an evidence-backed Atlas.
...more1riptide
Deployment-neutral Node.js agent runtime for private, structured LLM workloads.
ahmed-gamil-codes
Phone gateway for Claude Code and ChatGPT Codex — chat with your local coding-agent sessions from your phone over LAN, Tailscale, or Cloudflare.
...morehraedon
Keep agents at capability parity across harnesses (creds, E2E tooling) from one manifest
Muhammad Faqih Hakim
Selective memory layer for AI agents: importance-scored, self-decaying, pluggable.
A Python implementation of a minimalist Pi-style coding-agent harness.
CoinPaprika
LangChain tools for the DexPaprika API: keyless DEX market data across every supported blockchain
Finance District
Make your Saleor store shoppable by AI agents. Core protocol types, formatters, and payment handler interface for UCP and ACP.
...moreFinance District
Drop-in Next.js route handlers that expose your Saleor storefront to AI shopping agents via UCP and ACP protocols.
Ziro SDK — the agent engine (graph, tools, memory, RAG, guardrails, LLM adapters)